Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix prompt template unescaping #6399

Merged
merged 2 commits into from
Apr 10, 2023
Merged

Fix prompt template unescaping #6399

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dbe4a8e
Fix prompt template unescaping
MaximumEntropy Apr 10, 2023
3915588
Fix for when prompt template is None
MaximumEntropy Apr 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions nemo/collections/nlp/data/language_modeling/megatron/gpt_sft_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,9 @@ def __init__(
self.pad_to_max_length = pad_to_max_length
self.index_mapping_dir = index_mapping_dir
self.prompt_template = prompt_template
if self.prompt_template is not None:
# When providing things like newlines in the prompt template via the CLI, they are escaped. This line unescapes them.
self.prompt_template = self.prompt_template.encode('utf-8').decode('unicode_escape')
assert self.truncation_field in ["answer", "context"]

self.indexed_dataset = JSONLMemMapDataset(dataset_paths=[file_path], tokenizer=None, header_lines=0)
Expand Down